Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601ddf59eb17d457bcd4859c21d0edf409b6cfc1cf2de7c2263cb25251aee6a7
+oid sha256:ad3b8ba117ca2139468e811fbabd9d0a24e3c591d2cd6d13bc5ae5c8c1aaf377
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68ed6449418410d8343619d1c7844ab51d4de6d149475a8358883fd0738b0d63
+oid sha256:5bdca28e3db9d10c8d83a414cafffe9d55e3cf021cc455f2eb454ddfc5506244
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae0cadfe94dcf48c698c1b451b2c6352615de93dbee1916133fa523284b0d46
+oid sha256:e6b989fb58508466fe9075e0a573bc4dd7030a4a4f64885cc3af976ac95dcb55
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014147606696533837,
+  "epoch": 0.0028295213393067674,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 56.66,
       "eval_steps_per_second": 28.362,
       "step": 3
+    },
+    {
+      "epoch": 0.001886347559537845,
+      "grad_norm": 1.1900620460510254,
+      "learning_rate": 8e-05,
+      "loss": 1.63,
+      "step": 4
+    },
+    {
+      "epoch": 0.002357934449422306,
+      "grad_norm": 0.9931256175041199,
+      "learning_rate": 0.0001,
+      "loss": 1.2157,
+      "step": 5
+    },
+    {
+      "epoch": 0.0028295213393067674,
+      "grad_norm": 1.1468905210494995,
+      "learning_rate": 0.00012,
+      "loss": 1.5953,
+      "step": 6
+    },
+    {
+      "epoch": 0.0028295213393067674,
+      "eval_loss": 1.71695077419281,
+      "eval_runtime": 16.058,
+      "eval_samples_per_second": 55.611,
+      "eval_steps_per_second": 27.837,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 28937403236352.0,
+  "total_flos": 57874806472704.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null